Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    significant turns in conversation, likely indicating emotional or pivotal moments in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    comparing technical specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VersionUID
    -0.41
     colspan
    -0.36
     ...
    -0.35
     cubiertas
    -0.35
     Ull
    -0.34
     Bou
    -0.34
    creation
    -0.33
     inter
    -0.33
     Hau
    -0.33
     Scal
    -0.33
    POSITIVE LOGITS
     dAtA
    0.70
     يتيمه
    0.63
     betweenstory
    0.62
    :✨
    0.62
     resourceCulture
    0.59
    الحياه
    0.57
    ArrowToggle
    0.57
    脚注の使い方
    0.56
    PerformLayout
    0.55
    AnimationsModule
    0.53
    Act Density 0.475%

    No Known Activations